Unsupervised Few-Shot Learning

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

No dataset record in the archive lists this task.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

13 shown of 13 papers with code (22 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Self-Supervision Can Be a Good Few-Shot Learner
  19 Jul 2022 4 repositories listed Syntology ran 3 of 10 samples · 7 unverified
  Specifically, we maximize the mutual information (MI) of instances and their representations with a low-bias MI estimator to perform self-supervised pre-training.
• Self-Supervised Prototypical Transfer Learning for Few-Shot Classification
  19 Jun 2020 2 repositories listed Syntology ran 8 of 9 samples · 1 unverified · 4 pointer-only (licence)
  Building on these insights and on advances in self-supervised learning, we propose a transfer learning approach which constructs a metric embedding that clusters unlabeled prototypical samples and their augmentations…
• MICM: Rethinking Unsupervised Pretraining for Enhanced Few-shot Learning
  23 Aug 2024 1 repository listed
  Humans exhibit a remarkable ability to learn quickly from a limited number of labeled samples, a capability that starkly contrasts with that of current machine learning systems.
• BECLR: Batch Enhanced Contrastive Few-Shot Learning
  4 Feb 2024 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  Learning quickly from very few labeled samples is a fundamental attribute that separates machines and humans in the era of deep representation learning.
• Contrastive Prototypical Network with Wasserstein Confidence Penalty
  21 Oct 2022 1 repository listed
  This results in our CPN (Contrastive Prototypical Network) model, which combines the prototypical loss with pairwise contrast and outperforms the existing models from this paradigm with modestly large batch size.
• Self-Attention Message Passing for Contrastive Few-Shot Learning
  12 Oct 2022 1 repository listed
  Humans have a unique ability to learn new representations from just a handful of examples with little to no supervision.
• Trip-ROMA: Self-Supervised Learning with Triplets and Random Mappings
  22 Jul 2021 1 repository listed
  However, in small data regimes, we can not obtain a sufficient number of negative pairs or effectively avoid the over-fitting problem when negatives are not used at all.
• UVStyle-Net: Unsupervised Few-shot Learning of 3D Style Similarity Measure for B-Reps
  28 Apr 2021 1 repository listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  Boundary Representations (B-Reps) are the industry standard in 3D Computer Aided Design/Manufacturing (CAD/CAM) and industrial design due to their fidelity in representing stylistic details.
• Meta-GMVAE: Mixture of Gaussian VAE for Unsupervised Meta-Learning
  1 Jan 2021 1 repository listed
  Then, the learned model can be used for downstream few-shot classification tasks, where we obtain task-specific parameters by performing semi-supervised EM on the latent representations of the support and query set, and…
• Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Tasks
  30 Nov 2020 1 repository listed
  Meta-learning has become a practical approach towards few-shot image classification, where "a strategy to learn a classifier" is meta-learned on labeled base classes and can be applied to tasks with novel classes.
• Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation
  13 Apr 2020 1 repository listed Syntology ran 0 of 13 samples · 13 unverified
  Importantly, we highlight the value and importance of the distribution diversity in the augmentation-based pretext few-shot tasks, which can effectively alleviate the overfitting problem and make the few-shot model…
• Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning
  12 Jan 2020 1 repository listed
  The majority of existing few-shot learning methods describe image relations with binary labels.
• Program synthesis performance constrained by non-linear spatial relations in Synthetic Visual Reasoning Test
  18 Nov 2019 1 repository listed
  Here we re-considered the human and machine experiments, because they followed different protocols and yielded different statistics.

Syntology lines on 5 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.